Metraipolis › archive › dc_07ff350e783f
GAUGE: Group-Wise View-Inconsistency Rectification for Feed-Forward 4D Tracking — arXiv:2609.32596
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32596
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:00:25.856Z
- SHA-256 of the archived text
1c30931dc679b99014d74e3d248d02f561ac269406c1bcb257eac8c02d079d6a- Stable URL of this page
https://metraipolis.com/documento/dc_07ff350e783f
How to cite
GAUGE: Group-Wise View-Inconsistency Rectification for Feed-Forward 4D Tracking — arXiv:2609.32596 — arXiv (en), https://arxiv.org/abs/2609.32596 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_07ff350e783f (Metraipolis archive dc_07ff350e783f, sha256 1c30931dc679b99014d74e3d248d02f561ac269406c1bcb257eac8c02d079d6a)
BibTeX
@misc{dc07ff350e783f,
title = {GAUGE: Group-Wise View-Inconsistency Rectification for Feed-Forward 4D Tracking — arXiv:2609.32596},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32596},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_07ff350e783f; sha256 1c30931dc679b99014d74e3d248d02f561ac269406c1bcb257eac8c02d079d6a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32596. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Feed-forward models regress dense 3D point trajectories directly from monocular video, yet the residual after global alignment is substantial and lacks a structural explanation. Measured on dynamic query points across models and datasets, the error concentrates along the view direction, while the scale correction each motion group requires differs. The predicted displacement direction nevertheless supports reliable grouping, with a median angle far below the 90° random baseline. The systematic part of the residual is therefore a family of radial degrees of freedom per motion group, along directions 2D observations cannot constrain. We call it group-wise view inconsistency. We present GAUGE (Group-wise Adaptive Unsupervised Gauge Estimation), a training-free and model-agnostic post-hoc module. It recovers motion groups from direction consistency and spatial connectivity, then estimates a per-frame radial scale and group-level translation from 1% to 5% metric anchors, four degrees of freedom per group and frame. On dynamic query points of eight trackers, including D4RT, 4RC and SM4RT, our correction lowers endpoint error by 15.1% to 62.6% over the uncorrected predictions, while spending the same anchors on gradient fine-tuning improves the same models by only -1.1% to 15.2%. Code is publicly available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.32596 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:02.401Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).